Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Generalized treatment effects for clinical trials.

W W Hauck¹, T Hyslop, S Anderson

¹Biostatistics Section, Division of Clinical Pharmacology, Thomas Jefferson University, #1170, Philadelphia, PA 19107-5244, USA. w-hauck@lac.jci.tju.edu

Statistics in Medicine

|April 6, 2000

Summary

This study introduces a new method for analyzing clinical trial data, focusing on the probability that one treatment

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Study of charmless hadronic B meson decays to pseudoscalar-vector final states.

Physical review letters·2000

Same author

Optimal strategies for preventing progression of renal disease: should angiotensin converting enzyme inhibitors and angiotensin receptor blockers be used together?

Current hypertension reports·2000

Same author

Laparoscopic inguinal hernia repair: optimal technical variations and results in 1700 cases.

The American surgeon·2000

Same author

New techniques in fast time-resolved structure determination.

Cellular and molecular biology (Noisy-le-Grand, France)·2000

Same author

Patient desire and reasons for specialist referral in a gatekeeper-model managed care plan.

The American journal of managed care·2000

Same author

Effects of estrogen on leukocyte adhesion after transient forebrain ischemia.

Stroke·2000

Area of Science:

Clinical Trials
Biostatistics
Statistical Analysis

Background:

Current clinical trial analysis often focuses on mean or median response differences.
Treatments can impact response distributions beyond average values.

Purpose of the Study:

To develop a generalized treatment effect analysis for clinical trials.
To identify a parameter easily understood by clinicians.
To utilize confidence intervals for inference.

Main Methods:

Proposed a novel approach using reliability theory, targeting Pr[Y>X] (probability of one response exceeding another).
Compared this new approach with an existing method by O'Brien.
Evaluated performance under different variance and mean conditions.

Main Results:

The new approach and O'Brien's method show similar properties when rejecting the null hypothesis due to variance differences.
A key difference emerges when larger variance aligns with a larger mean; the new approach accounts for variance attenuating the mean effect.
The proposed method is readily applicable to positive control clinical equivalence trials.

Conclusions:

The novel Pr[Y>X] approach offers a clinically interpretable measure of treatment effect.
This method provides a more nuanced understanding of treatment effects on response distributions.
The approach is suitable for equivalence trials and enhances statistical analysis in clinical research.

Related Experiment Videos